Hello trend,
This is Satya Mallick from LearnOpenCV.com.
One of the first applications people learn when using OpenCV is Face Detection. There is a historical reason for that.
Object detection is hard.
The recent successes of object detectors make us forget how hard the problem used to be just a decade back.
The problem was considered so hard that early attempts at object detection focussed on specific objects instead of general purpose object detection. The first successful sub-class of problems that was solved reasonably well was the problem of Face Detection.
As a grad student, way back in 2003, I remember telling my advisor that in 5 years all digital cameras will have a face detector! I had just seen a demo camera at a conference and was super excited about it.
I was wrong! The field of CVML moved faster than I had anticipated.
Today, all you need to know is a programming language like Python or C++ and in just a few lines of code, you can have a face detector in your application.
But now we have a new problem. There are too many choices!
So, in today's post we are comparing many different Face Detectors (both Traditional and Deep Learning based) with their pros and cons. We also discuss about the different Benchmark datasets and metrics used for Face Detection. This guide should serve as a go-to resource whenever you are working on the problem of Face Detection.
Without further ado, let's get started.
| Face Detection - The Ultimate Guide |
You can check out the code by clicking on the button below, and star us on GitHub to say thanks!
| Download Code (GitHub) |
Highlights from the post
Check out the short video covering the highlights of the blog post:
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.